iommu/vt-d: Update DRHD/RMRR/ATSR device scope caches when PCI hotplug happens

Current Intel DMAR/IOMMU driver assumes that all PCI devices associated
with DMAR/RMRR/ATSR device scope arrays are created at boot time and
won't change at runtime, so it caches pointers of associated PCI device
object. That assumption may be wrong now due to:
1) introduction of PCI host bridge hotplug
2) PCI device hotplug through sysfs interfaces.

Wang Yijing has tried to solve this issue by caching <bus, dev, func>
tupple instead of the PCI device object pointer, but that's still
unreliable because PCI bus number may change in case of hotplug.
Please refer to http://lkml.org/lkml/2013/11/5/64
Message from Yingjing's mail:
after remove and rescan a pci device
[  611.857095] dmar: DRHD: handling fault status reg 2
[  611.857109] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff7000
[  611.857109] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.857524] dmar: DRHD: handling fault status reg 102
[  611.857534] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff6000
[  611.857534] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.857936] dmar: DRHD: handling fault status reg 202
[  611.857947] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff5000
[  611.857947] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.858351] dmar: DRHD: handling fault status reg 302
[  611.858362] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff4000
[  611.858362] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.860819] IPv6: ADDRCONF(NETDEV_UP): eth3: link is not ready
[  611.860983] dmar: DRHD: handling fault status reg 402
[  611.860995] dmar: INTR-REMAP: Request device [[86:00.3] fault index a4
[  611.860995] INTR-REMAP:[fault reason 34] Present field in the IRTE entry is clear

This patch introduces a new mechanism to update the DRHD/RMRR/ATSR device scope
caches by hooking PCI bus notification.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>

drivers/iommu/dmar.c

@@ -194,6 +194,209 @@ void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt)
 	*cnt = 0;
 }
 
+/* Optimize out kzalloc()/kfree() for normal cases */
+static char dmar_pci_notify_info_buf[64];
+
+static struct dmar_pci_notify_info *
+dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
+{
+	int level = 0;
+	size_t size;
+	struct pci_dev *tmp;
+	struct dmar_pci_notify_info *info;
+
+	BUG_ON(dev->is_virtfn);
+
+	/* Only generate path[] for device addition event */
+	if (event == BUS_NOTIFY_ADD_DEVICE)
+		for (tmp = dev; tmp; tmp = tmp->bus->self)
+			level++;
+
+	size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path);
+	if (size <= sizeof(dmar_pci_notify_info_buf)) {
+		info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
+	} else {
+		info = kzalloc(size, GFP_KERNEL);
+		if (!info) {
+			pr_warn("Out of memory when allocating notify_info "
+				"for %s.\n", pci_name(dev));
+			return NULL;
+		}
+	}
+
+	info->event = event;
+	info->dev = dev;
+	info->seg = pci_domain_nr(dev->bus);
+	info->level = level;
+	if (event == BUS_NOTIFY_ADD_DEVICE) {
+		for (tmp = dev, level--; tmp; tmp = tmp->bus->self) {
+			info->path[level].device = PCI_SLOT(tmp->devfn);
+			info->path[level].function = PCI_FUNC(tmp->devfn);
+			if (pci_is_root_bus(tmp->bus))
+				info->bus = tmp->bus->number;
+		}
+	}
+
+	return info;
+}
+
+static inline void dmar_free_pci_notify_info(struct dmar_pci_notify_info *info)
+{
+	if ((void *)info != dmar_pci_notify_info_buf)
+		kfree(info);
+}
+
+static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
+				struct acpi_dmar_pci_path *path, int count)
+{
+	int i;
+
+	if (info->bus != bus)
+		return false;
+	if (info->level != count)
+		return false;
+
+	for (i = 0; i < count; i++) {
+		if (path[i].device != info->path[i].device ||
+		    path[i].function != info->path[i].function)
+			return false;
+	}
+
+	return true;
+}
+
+/* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
+int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+			  void *start, void*end, u16 segment,
+			  struct pci_dev __rcu **devices, int devices_cnt)
+{
+	int i, level;
+	struct pci_dev *tmp, *dev = info->dev;
+	struct acpi_dmar_device_scope *scope;
+	struct acpi_dmar_pci_path *path;
+
+	if (segment != info->seg)
+		return 0;
+
+	for (; start < end; start += scope->length) {
+		scope = start;
+		if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		    scope->entry_type != ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			continue;
+
+		path = (struct acpi_dmar_pci_path *)(scope + 1);
+		level = (scope->length - sizeof(*scope)) / sizeof(*path);
+		if (!dmar_match_pci_path(info, scope->bus, path, level))
+			continue;
+
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
+		    (dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+			pr_warn("Device scope type does not match for %s\n",
+				pci_name(dev));
+			return -EINVAL;
+		}
+
+		for_each_dev_scope(devices, devices_cnt, i, tmp)
+			if (tmp == NULL) {
+				rcu_assign_pointer(devices[i],
+						   pci_dev_get(dev));
+				return 1;
+			}
+		BUG_ON(i >= devices_cnt);
+	}
+
+	return 0;
+}
+
+int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
+			  struct pci_dev __rcu **devices, int count)
+{
+	int index;
+	struct pci_dev *tmp;
+
+	if (info->seg != segment)
+		return 0;
+
+	for_each_active_dev_scope(devices, count, index, tmp)
+		if (tmp == info->dev) {
+			rcu_assign_pointer(devices[index], NULL);
+			synchronize_rcu();
+			pci_dev_put(tmp);
+			return 1;
+		}
+
+	return 0;
+}
+
+static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	for_each_drhd_unit(dmaru) {
+		if (dmaru->include_all)
+			continue;
+
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit, header);
+		ret = dmar_insert_dev_scope(info, (void *)(drhd + 1),
+				((void *)drhd) + drhd->header.length,
+				dmaru->segment,
+				dmaru->devices, dmaru->devices_cnt);
+		if (ret != 0)
+			break;
+	}
+	if (ret >= 0)
+		ret = dmar_iommu_notify_scope_dev(info);
+
+	return ret;
+}
+
+static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	for_each_drhd_unit(dmaru)
+		if (dmar_remove_dev_scope(info, dmaru->segment,
+			dmaru->devices, dmaru->devices_cnt))
+			break;
+	dmar_iommu_notify_scope_dev(info);
+}
+
+static int dmar_pci_bus_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(data);
+	struct dmar_pci_notify_info *info;
+
+	/* Only care about add/remove events for physical functions */
+	if (pdev->is_virtfn)
+		return NOTIFY_DONE;
+	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+		return NOTIFY_DONE;
+
+	info = dmar_alloc_pci_notify_info(pdev, action);
+	if (!info)
+		return NOTIFY_DONE;
+
+	down_write(&dmar_global_lock);
+	if (action == BUS_NOTIFY_ADD_DEVICE)
+		dmar_pci_bus_add_dev(info);
+	else if (action == BUS_NOTIFY_DEL_DEVICE)
+		dmar_pci_bus_del_dev(info);
+	up_write(&dmar_global_lock);
+
+	dmar_free_pci_notify_info(info);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dmar_pci_bus_nb = {
+	.notifier_call = dmar_pci_bus_notifier,
+	.priority = INT_MIN,
+};
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
@@ -482,6 +685,8 @@ int __init dmar_dev_scope_init(void)
 	if (ret)
 		goto fail;
 
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
 	dmar_dev_scope_initialized = 1;
 	return 0;
 
@@ -1412,6 +1617,8 @@ static int __init dmar_free_unused_resources(void)
 	if (irq_remapping_enabled || intel_iommu_enabled)
 		return 0;
 
+	bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
 	down_write(&dmar_global_lock);
 	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
 		list_del(&dmaru->list);

drivers/iommu/intel-iommu.c

@@ -3625,6 +3625,60 @@ int __init dmar_parse_rmrr_atsr_dev(void)
 	return 0;
 }
 
+int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_rmrr_unit *rmrru;
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_reserved_memory *rmrr;
+
+	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+		return 0;
+
+	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
+		rmrr = container_of(rmrru->hdr,
+				    struct acpi_dmar_reserved_memory, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				rmrr->segment, rmrru->devices,
+				rmrru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt))
+				break;
+		}
+	}
+
+	list_for_each_entry(atsru, &dmar_atsr_units, list) {
+		if (atsru->include_all)
+			continue;
+
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
+					(void *)atsr + atsr->header.length,
+					atsr->segment, atsru->devices,
+					atsru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, atsr->segment,
+					atsru->devices, atsru->devices_cnt))
+				break;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Here we only respond to action of unbound device from driver.
  *

include/linux/dmar.h

@@ -50,6 +50,15 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_notify_info {
+	struct pci_dev			*dev;
+	unsigned long			event;
+	int				bus;
+	u16				seg;
+	u16				level;
+	struct acpi_dmar_pci_path	path[];
+}  __attribute__((packed));
+
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
@@ -89,12 +98,18 @@ extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
 				struct pci_dev ***devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
 extern void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt);
-extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
-
+extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+				 void *start, void*end, u16 segment,
+				 struct pci_dev __rcu **devices,
+				 int devices_cnt);
+extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
+				 u16 segment, struct pci_dev __rcu **devices,
+				 int count);
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 #else
+struct dmar_pci_notify_info;
 static inline int detect_intel_iommu(void)
 {
 	return -ENODEV;
@@ -161,6 +176,7 @@ extern int iommu_detected, no_iommu;
 extern int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 extern int intel_iommu_init(void);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
@@ -176,6 +192,10 @@ static inline int dmar_parse_rmrr_atsr_dev(void)
 {
 	return 0;
 }
+static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
+{
+	return 0;
+}
 #endif /* CONFIG_INTEL_IOMMU */
 
 #endif /* __DMAR_H__ */